Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9f11be156356f414dd34923f20713c094208c1202abf9e98d5ec7fb79de3138
+oid sha256:86b280c727e5ee5e7534e19832eadbef15dafd122763276af4f77d1124b554b1
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33cafa734a71c5e4c4795ec6a3b8bfb4c46e21a0cfc1ce27753be79fd87927a2
+oid sha256:226b8828b9dcdf1de0c3a1814add629b14c5b081db6564f144048001a828139f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2fe91e4b71ad96971401f0069a1c0bd726c6e3d3f180c7c5724b4adc2dcccdc
+oid sha256:7170a2d9b24ecc77552af509fa5ca848d0a66f21c29b073517cc02fd19368fe3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021998166819431713,
+  "epoch": 0.03299725022914757,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 9.472,
       "eval_steps_per_second": 4.777,
       "step": 6
+    },
+    {
+      "epoch": 0.025664527956003668,
+      "grad_norm": 21.698095321655273,
+      "learning_rate": 0.00014,
+      "loss": 8.2158,
+      "step": 7
+    },
+    {
+      "epoch": 0.02933088909257562,
+      "grad_norm": 32.11186218261719,
+      "learning_rate": 0.00016,
+      "loss": 6.0142,
+      "step": 8
+    },
+    {
+      "epoch": 0.03299725022914757,
+      "grad_norm": 14.958884239196777,
+      "learning_rate": 0.00018,
+      "loss": 2.9791,
+      "step": 9
+    },
+    {
+      "epoch": 0.03299725022914757,
+      "eval_loss": 2.25606632232666,
+      "eval_runtime": 12.2047,
+      "eval_samples_per_second": 9.423,
+      "eval_steps_per_second": 4.752,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109738548887552.0,
+  "total_flos": 1664607823331328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null